freebsd-src/sys/contrib/dpdk_rte_lpm/rte_lpm.h
Alexander V. Chernikov 537d134373 Bring DPDK route lookups to FreeBSD.
This change introduces loadable fib lookup modules based on
 DPDK rte_lpm lib targeted for high-speed lookups in large-scale tables.
It is based on the lookup framework described in D27401.

IPv4 module is called dpdk_lpm4. It wraps around rte_lpm [1] library.
This library implements variation of DIR24-8 [2] lookup algorithm.
Module provide lockless route lookups and in-place incremental updates,
 allowing for good RIB performance.

IPv6 module is called dpdk_lpm6. It wraps around rte_lpm6 [3] library.
Implementation can be seen as multi-bit trie where the stride or number of bits
 inspected on each level varies from level to level.
It can vary from 1 to 14 memory accesses, with 5 being the average value
 for the lengths that are most commonly used in IPv6.
Module provide lockless route lookups for global unicast addresses
 and in-place incremental updates, allowing for good RIB performance.

Implementation details:
* wrapper code lives in `sys/contrib/dpdk_rte_lpm/dpdk_lpm[6].c`.
* rte_lpm[6] implementation contains both RIB and FIB code.
 . RIB ("rule_") code, backed by array of hash tables part has been commented out,
 as base radix already provides all the necessary primitives.
* link-local lookups are currently implemented as base radix lookup.
 This part should be converted to something like read-only radix trie.

Usage detail:
Compile kernel with option FIB_ALGO and load dpdk_lpm4/dpdk_lpm6
 module at any time. They will be picked up automatically when
 amount of routes raises to several thousand.

[1]: https://doc.dpdk.org/guides/prog_guide/lpm_lib.html
[2]: http://yuba.stanford.edu/~nickm/papers/Infocom98_lookup.pdf
[3]: https://doc.dpdk.org/guides/prog_guide/lpm6_lib.html

Differential Revision: https://reviews.freebsd.org/D27412
2021-01-09 12:41:04 +00:00

404 lines
11 KiB
C

/* SPDX-License-Identifier: BSD-3-Clause
* Copyright(c) 2010-2014 Intel Corporation
*/
#ifndef _RTE_LPM_H_
#define _RTE_LPM_H_
/**
* @file
* RTE Longest Prefix Match (LPM)
*/
/*
#include <errno.h>
#include <sys/queue.h>
#include <stdint.h>
#include <stdlib.h>
#include <rte_branch_prediction.h>
#include <rte_byteorder.h>
#include <rte_config.h>
#include <rte_memory.h>
#include <rte_common.h>
#include <rte_vect.h>
*/
#include "rte_branch_prediction.h"
#ifdef __cplusplus
extern "C" {
#endif
/** Max number of characters in LPM name. */
#define RTE_LPM_NAMESIZE 16
/** Maximum depth value possible for IPv4 LPM. */
#define RTE_LPM_MAX_DEPTH 32
/** @internal Total number of tbl24 entries. */
#define RTE_LPM_TBL24_NUM_ENTRIES (1 << 24)
/** @internal Number of entries in a tbl8 group. */
#define RTE_LPM_TBL8_GROUP_NUM_ENTRIES 256
/** @internal Max number of tbl8 groups in the tbl8. */
#define RTE_LPM_MAX_TBL8_NUM_GROUPS (1 << 24)
/** @internal Total number of tbl8 groups in the tbl8. */
#define RTE_LPM_TBL8_NUM_GROUPS 256
/** @internal Total number of tbl8 entries. */
#define RTE_LPM_TBL8_NUM_ENTRIES (RTE_LPM_TBL8_NUM_GROUPS * \
RTE_LPM_TBL8_GROUP_NUM_ENTRIES)
/** @internal Macro to enable/disable run-time checks. */
#if defined(RTE_LIBRTE_LPM_DEBUG)
#define RTE_LPM_RETURN_IF_TRUE(cond, retval) do { \
if (cond) return (retval); \
} while (0)
#else
#define RTE_LPM_RETURN_IF_TRUE(cond, retval)
#endif
/** @internal bitmask with valid and valid_group fields set */
#define RTE_LPM_VALID_EXT_ENTRY_BITMASK 0x03000000
/** Bitmask used to indicate successful lookup */
#define RTE_LPM_LOOKUP_SUCCESS 0x01000000
#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
/** @internal Tbl24 entry structure. */
__extension__
struct rte_lpm_tbl_entry {
/**
* Stores Next hop (tbl8 or tbl24 when valid_group is not set) or
* a group index pointing to a tbl8 structure (tbl24 only, when
* valid_group is set)
*/
uint32_t next_hop :24;
/* Using single uint8_t to store 3 values. */
uint32_t valid :1; /**< Validation flag. */
/**
* For tbl24:
* - valid_group == 0: entry stores a next hop
* - valid_group == 1: entry stores a group_index pointing to a tbl8
* For tbl8:
* - valid_group indicates whether the current tbl8 is in use or not
*/
uint32_t valid_group :1;
uint32_t depth :6; /**< Rule depth. */
};
#else
__extension__
struct rte_lpm_tbl_entry {
uint32_t depth :6;
uint32_t valid_group :1;
uint32_t valid :1;
uint32_t next_hop :24;
};
#endif
/** LPM configuration structure. */
struct rte_lpm_config {
uint32_t max_rules; /**< Max number of rules. */
uint32_t number_tbl8s; /**< Number of tbl8s to allocate. */
int flags; /**< This field is currently unused. */
};
/** @internal Rule structure. */
struct rte_lpm_rule {
uint32_t ip; /**< Rule IP address. */
uint32_t next_hop; /**< Rule next hop. */
};
/** @internal Contains metadata about the rules table. */
struct rte_lpm_rule_info {
uint32_t used_rules; /**< Used rules so far. */
uint32_t first_rule; /**< Indexes the first rule of a given depth. */
};
struct nhop_object;
struct rte_lpm_external {
struct nhop_object **nh_idx; /**< # -> idx mappings */
uint32_t default_idx; /* nhop index of default route */
uint32_t fibnum; /* fib index */
};
/** @internal LPM structure. */
struct rte_lpm {
/* LPM metadata. */
struct rte_lpm_external ext;
char name[RTE_LPM_NAMESIZE]; /**< Name of the lpm. */
uint32_t max_rules; /**< Max. balanced rules per lpm. */
uint32_t number_tbl8s; /**< Number of tbl8s. */
struct rte_lpm_rule_info rule_info[RTE_LPM_MAX_DEPTH]; /**< Rule info table. */
/* LPM Tables. */
struct rte_lpm_tbl_entry tbl24[RTE_LPM_TBL24_NUM_ENTRIES]
__rte_cache_aligned; /**< LPM tbl24 table. */
struct rte_lpm_tbl_entry *tbl8; /**< LPM tbl8 table. */
struct rte_lpm_rule *rules_tbl; /**< LPM rules. */
};
/**
* Create an LPM object.
*
* @param name
* LPM object name
* @param socket_id
* NUMA socket ID for LPM table memory allocation
* @param config
* Structure containing the configuration
* @return
* Handle to LPM object on success, NULL otherwise with rte_errno set
* to an appropriate values. Possible rte_errno values include:
* - E_RTE_NO_CONFIG - function could not get pointer to rte_config structure
* - E_RTE_SECONDARY - function was called from a secondary process instance
* - EINVAL - invalid parameter passed to function
* - ENOSPC - the maximum number of memzones has already been allocated
* - EEXIST - a memzone with the same name already exists
* - ENOMEM - no appropriate memory area found in which to create memzone
*/
struct rte_lpm *
rte_lpm_create(const char *name, int socket_id,
const struct rte_lpm_config *config);
/**
* Find an existing LPM object and return a pointer to it.
*
* @param name
* Name of the lpm object as passed to rte_lpm_create()
* @return
* Pointer to lpm object or NULL if object not found with rte_errno
* set appropriately. Possible rte_errno values include:
* - ENOENT - required entry not available to return.
*/
struct rte_lpm *
rte_lpm_find_existing(const char *name);
/**
* Free an LPM object.
*
* @param lpm
* LPM object handle
* @return
* None
*/
void
rte_lpm_free(struct rte_lpm *lpm);
/**
* Add a rule to the LPM table.
*
* @param lpm
* LPM object handle
* @param ip
* IP of the rule to be added to the LPM table
* @param depth
* Depth of the rule to be added to the LPM table
* @param next_hop
* Next hop of the rule to be added to the LPM table
* @return
* 0 on success, negative value otherwise
*/
int
rte_lpm_add(struct rte_lpm *lpm, uint32_t ip, uint8_t depth, uint32_t next_hop);
/**
* Check if a rule is present in the LPM table,
* and provide its next hop if it is.
*
* @param lpm
* LPM object handle
* @param ip
* IP of the rule to be searched
* @param depth
* Depth of the rule to searched
* @param next_hop
* Next hop of the rule (valid only if it is found)
* @return
* 1 if the rule exists, 0 if it does not, a negative value on failure
*/
int
rte_lpm_is_rule_present(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
uint32_t *next_hop);
/**
* Delete a rule from the LPM table.
*
* @param lpm
* LPM object handle
* @param ip
* IP of the rule to be deleted from the LPM table
* @param depth
* Depth of the rule to be deleted from the LPM table
* @param psub_rule_depth
* Pointer to depth of the parent rule
* @param sub_rule_nhop
* Pinter to the parent rule nexthop index
* @return
* 0 on success, negative value otherwise
*/
int
rte_lpm_delete(struct rte_lpm *lpm, uint32_t ip, uint8_t depth,
uint8_t sub_rule_depth, uint32_t sub_rule_nhop);
/**
* Delete all rules from the LPM table.
*
* @param lpm
* LPM object handle
*/
void
rte_lpm_delete_all(struct rte_lpm *lpm);
/**
* Lookup an IP into the LPM table.
*
* @param lpm
* LPM object handle
* @param ip
* IP to be looked up in the LPM table
* @param next_hop
* Next hop of the most specific rule found for IP (valid on lookup hit only)
* @return
* -EINVAL for incorrect arguments, -ENOENT on lookup miss, 0 on lookup hit
*/
static inline int
rte_lpm_lookup(struct rte_lpm *lpm, uint32_t ip, uint32_t *next_hop)
{
unsigned tbl24_index = (ip >> 8);
uint32_t tbl_entry;
const uint32_t *ptbl;
/* DEBUG: Check user input arguments. */
RTE_LPM_RETURN_IF_TRUE(((lpm == NULL) || (next_hop == NULL)), -EINVAL);
/* Copy tbl24 entry */
ptbl = (const uint32_t *)(&lpm->tbl24[tbl24_index]);
tbl_entry = *ptbl;
/* Memory ordering is not required in lookup. Because dataflow
* dependency exists, compiler or HW won't be able to re-order
* the operations.
*/
/* Copy tbl8 entry (only if needed) */
if (unlikely((tbl_entry & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
unsigned tbl8_index = (uint8_t)ip +
(((uint32_t)tbl_entry & 0x00FFFFFF) *
RTE_LPM_TBL8_GROUP_NUM_ENTRIES);
ptbl = (const uint32_t *)&lpm->tbl8[tbl8_index];
tbl_entry = *ptbl;
}
*next_hop = ((uint32_t)tbl_entry & 0x00FFFFFF);
return (tbl_entry & RTE_LPM_LOOKUP_SUCCESS) ? 0 : -ENOENT;
}
/**
* Lookup multiple IP addresses in an LPM table. This may be implemented as a
* macro, so the address of the function should not be used.
*
* @param lpm
* LPM object handle
* @param ips
* Array of IPs to be looked up in the LPM table
* @param next_hops
* Next hop of the most specific rule found for IP (valid on lookup hit only).
* This is an array of two byte values. The most significant byte in each
* value says whether the lookup was successful (bitmask
* RTE_LPM_LOOKUP_SUCCESS is set). The least significant byte is the
* actual next hop.
* @param n
* Number of elements in ips (and next_hops) array to lookup. This should be a
* compile time constant, and divisible by 8 for best performance.
* @return
* -EINVAL for incorrect arguments, otherwise 0
*/
#define rte_lpm_lookup_bulk(lpm, ips, next_hops, n) \
rte_lpm_lookup_bulk_func(lpm, ips, next_hops, n)
static inline int
rte_lpm_lookup_bulk_func(const struct rte_lpm *lpm, const uint32_t *ips,
uint32_t *next_hops, const unsigned n)
{
unsigned i;
unsigned tbl24_indexes[n];
const uint32_t *ptbl;
/* DEBUG: Check user input arguments. */
RTE_LPM_RETURN_IF_TRUE(((lpm == NULL) || (ips == NULL) ||
(next_hops == NULL)), -EINVAL);
for (i = 0; i < n; i++) {
tbl24_indexes[i] = ips[i] >> 8;
}
for (i = 0; i < n; i++) {
/* Simply copy tbl24 entry to output */
ptbl = (const uint32_t *)&lpm->tbl24[tbl24_indexes[i]];
next_hops[i] = *ptbl;
/* Overwrite output with tbl8 entry if needed */
if (unlikely((next_hops[i] & RTE_LPM_VALID_EXT_ENTRY_BITMASK) ==
RTE_LPM_VALID_EXT_ENTRY_BITMASK)) {
unsigned tbl8_index = (uint8_t)ips[i] +
(((uint32_t)next_hops[i] & 0x00FFFFFF) *
RTE_LPM_TBL8_GROUP_NUM_ENTRIES);
ptbl = (const uint32_t *)&lpm->tbl8[tbl8_index];
next_hops[i] = *ptbl;
}
}
return 0;
}
/* Mask four results. */
#define RTE_LPM_MASKX4_RES UINT64_C(0x00ffffff00ffffff)
/**
* Lookup four IP addresses in an LPM table.
*
* @param lpm
* LPM object handle
* @param ip
* Four IPs to be looked up in the LPM table
* @param hop
* Next hop of the most specific rule found for IP (valid on lookup hit only).
* This is an 4 elements array of two byte values.
* If the lookup was successful for the given IP, then least significant byte
* of the corresponding element is the actual next hop and the most
* significant byte is zero.
* If the lookup for the given IP failed, then corresponding element would
* contain default value, see description of then next parameter.
* @param defv
* Default value to populate into corresponding element of hop[] array,
* if lookup would fail.
*/
#if 0
static inline void
rte_lpm_lookupx4(const struct rte_lpm *lpm, xmm_t ip, uint32_t hop[4],
uint32_t defv);
#if defined(RTE_ARCH_ARM) || defined(RTE_ARCH_ARM64)
#include "rte_lpm_neon.h"
#elif defined(RTE_ARCH_PPC_64)
#include "rte_lpm_altivec.h"
#else
#include "rte_lpm_sse.h"
#endif
#endif
#ifdef __cplusplus
}
#endif
#endif /* _RTE_LPM_H_ */